DIFFERENTIAL PATHWAY DEPENDENCY DISCOVERY ASSOCIATED WITH DRUG RESPONSE ACROSS CANCER CELL LINES

Computational repurposing of therapeutic small molecules from cancer to pulmonary hypertension

Cancer therapies are being considered for treating rare noncancerous diseases like pulmonary hypertension (PH), but effective computational screening is lacking. Via transcriptomic differential dependency analyses leveraging parallels between cancer and PH, we mapped a landscape of cancer drug functions dependent upon rewiring of PH gene clusters. Bromodomain and extra-terminal motif (BET) protein inhibitors were predicted to rely upon several gene clusters inclusive of galectin-8 (LGALS8). Correspondingly, LGALS8 was found to mediate the BET inhibitor–dependent control of endothelial apoptosis, an essential role for PH in vivo. Separately, a piperlongumine analog’s actions were predicted to depend upon the iron-sulfur biogenesis gene ISCU. Correspondingly, the analog was found to inhibit ISCU glutathionylation, rescuing oxidative metabolism, decreasing endothelial apoptosis, and improving PH. Thus, we identified crucial drug-gene axes central to endothelial dysfunction and therapeutic priorities for PH. These results establish a wide-ranging, network dependency platform to redefine cancer drugs for use in noncancerous conditions.

Current Advances and Limitations of Deep Learning in Anticancer Drug Sensitivity Prediction

Anticancer drug screening can accelerate drug discovery to save the lives of cancer patients, but cancer heterogeneity makes this screening challenging. The prediction of anticancer drug sensitivity is useful for anticancer drug development and the identification of biomarkers of drug sensitivity. Deep learning, as a branch of machine learning, is an important aspect of in silico research. Its outstanding computational performance means that it has been used for many biomedical purposes, such as medical image interpretation, biological sequence analysis, and drug discovery. Several studies have predicted anticancer drug sensitivity based on deep learning algorithms. The field of deep learning has made progress regarding model performance and multi-omics data integration. However, deep learning is limited by the number of studies performed and data sources available, so it is not perfect as a pre-clinical approach for use in the anticancer drug screening process. Improving the performance of deep learning models is a pressing issue for researchers. In this review, we introduce the research of anticancer drug sensitivity prediction and the use of deep learning in this research area. To provide a reference for future research, we also review some common data sources and machine learning methods. Lastly, we discuss the advantages and disadvantages of deep learning, as well as the limitations and future perspectives regarding this approach.

Drug Selection via Joint Push and Learning to Rank

Selecting the right drugs for the right patients is a primary goal of precision medicine. In this article, we consider the problem of cancer drug selection in a learning-to-rank framework. We have formulated the cancer drug selection problem as to accurately predicting 1) the ranking positions of sensitive drugs and 2) the ranking orders among sensitive drugs in cancer cell lines based on their responses to cancer drugs. We have developed a new learning-to-rank method, denoted as pLETORg, that predicts drug ranking structures in each cell line via using drug latent vectors and cell line latent vectors. The pLETORg method learns such latent vectors through explicitly enforcing that, in the drug ranking list of each cell line, the sensitive drugs are pushed above insensitive drugs, and meanwhile the ranking orders among sensitive drugs are correct. Genomics information on cell lines is leveraged in learning the latent vectors. Our experimental results on a benchmark cell line-drug response dataset demonstrate that the new pLETORg significantly outperforms the state-of-the-art method in prioritizing new sensitive drugs.

IPCT: Integrated Pharmacogenomic Platform of Human Cancer Cell Lines and Tissues

: (1) Motivation: The exponential increase in multilayered data, including omics, pathways, chemicals, and experimental models, requires innovative strategies to identify new linkages between drug response information and omics features. Despite the availability of databases such as the Cancer Cell Line Encyclopedia (CCLE), the Cancer Therapeutics Response Portal (CTRP), and The Cancer Genome Atlas (TCGA), it is still challenging for biologists to explore the relationship between drug response and underlying genomic features due to the heterogeneity of the data. In light of this, the Integrated Pharmacogenomic Database of Cancer Cell Lines and Tissues (IPCT) has been developed as a user-friendly way to identify new linkages between drug responses and genomic features, as these findings can lead not only to new biological discoveries but also to new clinical trials. (2) Results: The IPCT allows biologists to compare the genomic features of sensitive cell lines or small molecules with the genomic features of tumor tissues by integrating the CTRP and CCLE databases with the REACTOME, cBioPortal, and Expression Atlas databases. The input consists of a list of small molecules, cell lines, or genes, and the output is a graph containing data entities connected with the queried input. Users can apply filters to the databases, pathways, and genes as well as select computed sensitivity values and mutation frequency scores to generate a relevant graph. Different objects are differentiated based on the background color of the nodes. Moreover, when multiple small molecules, cell lines, or genes are input, users can see their shared connections to explore the data entities common between them. Finally, users can view the resulting graphs in the online interface or download them in multiple image or graph formats. (3) Availability and Implementation: The IPCT is available as a web application with an integrated MySQL database. The web application was developed using Java and deployed on the Tomcat server. The user interface was developed using HTML5, JQuery v.3.1.0 , and the Cytoscape Graph API v.1.0.4. The IPCT can be accessed at http://ipct.ewostech.net. The source code is available at https://github.com/muhammadshoaib/ipct.

Computational Analyses Connect Small-Molecule Sensitivity to Cellular Features Using Large Panels of Cancer Cell Lines

We recently pioneered several analyses of small-molecule sensitivity data collected from large-scale perturbation of hundreds of cancer cell lines with hundreds of small molecules, with cell viability measured as a readout of compound sensitivity. We performed these studies using cancer cell lines previously annotated with cellular, genomic, and basal gene-expression features. By combining small-molecule sensitivity data with these other datasets, we identified new candidate biomarkers of sensitivity, gained insights into small-molecule mechanisms of action, and proposed candidate hypotheses for cancer dependencies (including candidate combination therapies). Nevertheless, given the size of these datasets, we expect that many connections between cellular features and small-molecule sensitivity remain underexplored. In this chapter, we provide a step-by-step account of foundational data-analysis methods underlying our published studies, including working MATLAB code applied to our own public datasets. These procedures will allow others to repeat analyses of our data with new parameters, in additional contexts, and to adapt our procedures to their own datasets.

Contextualization of drug-mediator relations using evidence networks

Background

Genomic analysis of drug response can provide unique insights into therapies that can be used to match the “right drug to the right patient.” However, the process of discovering such therapeutic insights using genomic data is not straightforward and represents an area of active investigation. EDDY (Evaluation of Differential DependencY), a statistical test to detect differential statistical dependencies, is one method that leverages genomic data to identify differential genetic dependencies. EDDY has been used in conjunction with the Cancer Therapeutics Response Portal (CTRP), a dataset with drug-response measurements for more than 400 small molecules, and RNAseq data of cell lines in the Cancer Cell Line Encyclopedia (CCLE) to find potential drug-mediator pairs. Mediators were identified as genes that showed significant change in genetic statistical dependencies within annotated pathways between drug sensitive and drug non-sensitive cell lines, and the results are presented as a public web-portal (EDDY-CTRP). However, the interpretability of drug-mediator pairs currently hinders further exploration of these potentially valuable results.

Methods

In this study, we address this challenge by constructing evidence networks built with protein and drug interactions from the STITCH and STRING interaction databases. STITCH and STRING are sister databases that catalog known and predicted drug-protein interactions and protein-protein interactions, respectively. Using these two databases, we have developed a method to construct evidence networks to “explain” the relation between a drug and a mediator. 

Results

We applied this approach to drug-mediator relations discovered in EDDY-CTRP analysis and identified evidence networks for ~70% of drug-mediator pairs where most mediators were not known direct targets for the drug. Constructed evidence networks enable researchers to contextualize the drug-mediator pair with current research and knowledge. Using evidence networks, we were able to improve the interpretability of the EDDY-CTRP results by linking the drugs and mediators with genes associated with both the drug and the mediator.

Conclusion

We anticipate that these evidence networks will help inform EDDY-CTRP results and enhance the generation of important insights to drug sensitivity that will lead to improved precision medicine applications.